sim_platform.research.portfolio¶
Portfolio construction: from signals or returns to weights, share targets and orders.
Pure functions over plain lists and dictionaries, so they work in a notebook, in a model file’s own environment (copy this module) and in an Agent’s local tool.
Weights:
equal_weights,inverse_volatility,risk_parity,minimum_variance(long only) andsignal_weights(scale signals to a gross).Risk:
volatility_targetscales weights to a target annual volatility, andapply_limitscaps each weight, the gross and the net exposure.Execution:
target_sharesturns weights into whole shares at given prices, andrebalance_orderslists the buys and sells that move holdings to the targets.
Money and prices are integers in ten-thousandths of a dollar, as everywhere in Market Lab; returns are decimals per period.
- sim_platform.research.portfolio.equal_weights(symbols)[source]¶
1/n in each symbol.
- Parameters:
symbols (Sequence[str])
- Return type:
Dict[str, float]
- sim_platform.research.portfolio.inverse_volatility(returns)[source]¶
Weights proportional to 1/volatility, summing to one.
- Parameters:
returns (Mapping[str, Sequence[float]])
- Return type:
Dict[str, float]
- sim_platform.research.portfolio.risk_parity(returns, *, iterations=500, tolerance=1e-10)[source]¶
Long-only weights where each asset contributes equally to portfolio variance.
Solved by the multiplicative fixed point w_i <- w_i * (1/n) / (w_i (Σw)_i / w’Σw), started from inverse volatility.
- Parameters:
returns (Mapping[str, Sequence[float]])
iterations (int)
tolerance (float)
- Return type:
Dict[str, float]
- sim_platform.research.portfolio.minimum_variance(returns, *, iterations=2000, step=None)[source]¶
Long-only, fully invested minimum-variance weights by projected gradient descent.
- Parameters:
returns (Mapping[str, Sequence[float]])
iterations (int)
step (float | None)
- Return type:
Dict[str, float]
- sim_platform.research.portfolio.signal_weights(signals, *, gross=1.0)[source]¶
Scale signals (any sign) so absolute weights sum to
gross; zeros stay zero.- Parameters:
signals (Mapping[str, float])
gross (float)
- Return type:
Dict[str, float]
- sim_platform.research.portfolio.portfolio_volatility(weights, returns, periods_per_year)[source]¶
Annualised volatility of a weighted portfolio from per-period returns.
- Parameters:
weights (Mapping[str, float])
returns (Mapping[str, Sequence[float]])
periods_per_year (float)
- Return type:
float
- sim_platform.research.portfolio.volatility_target(weights, returns, *, target, periods_per_year=252, max_leverage=1.0)[source]¶
Scale weights so the portfolio’s annual volatility is
target(capped leverage).- Parameters:
weights (Mapping[str, float])
returns (Mapping[str, Sequence[float]])
target (float)
periods_per_year (float)
max_leverage (float)
- Return type:
Dict[str, float]
- sim_platform.research.portfolio.apply_limits(weights, *, max_weight=None, max_gross=None, max_net=None)[source]¶
Cap each absolute weight, then scale down to the gross and net limits.
- Parameters:
weights (Mapping[str, float])
max_weight (float | None)
max_gross (float | None)
max_net (float | None)
- Return type:
Dict[str, float]
Whole shares (in multiples of
lot) closest below each weight ofequity.- Parameters:
weights (Mapping[str, float])
prices (Mapping[str, int])
equity (int)
lot (int)
- Return type:
Dict[str, int]
- sim_platform.research.portfolio.rebalance_orders(current, target, *, min_shares=1)[source]¶
Buys and sells that move
currentholdings totarget, sells first.Each order is
{'symbol', 'side', 'quantity'}; changes smaller thanmin_sharesare skipped to avoid paying costs for noise.- Parameters:
current (Mapping[str, int])
target (Mapping[str, int])
min_shares (int)
- Return type:
List[Dict[str, object]]